prithivMLmods/Qwen3-VL-8B-Heretic-Stable

Same weights, repacked vs prithivMLmods/Qwen3-VL-8B-Instruct-Unredacted-MAX. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/261, MLP 0/232, Attention 0/252

3 derivatives checked

• prithivMLmods/Qwen3-VL-8B-Heretic-Stable-GGUF: Same weights, converted (fewer layers)
• mradermacher/Qwen3-VL-8B-Heretic-Stable-i1-GGUF: Quantization (fewer layers)
• mradermacher/Qwen3-VL-8B-Heretic-Stable-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse